What problem does it solve? Turning informal bug reports from a QA session into well-structured, durable GitHub issues is tedious and often produces tickets that reference fragile file paths or lack reproduction steps. This Skill runs an interactive QA session where you describe problems conversationally while the agent explores the codebase for context and files clean, user-focused issues automatically. ## Core Features & Use Cases - Conversational bug intake: Describe problems in your own words with at most 2-3 short clarifying questions, no over-interviewing. - Background codebase exploration: Learns the project's domain language and expected behavior so issues read naturally without citing files or line numbers. - Smart issue breakdown: Splits multi-part reports into thin, independently fixable issues with honest blocking relationships, filed in dependency order via gh issue create. - Use Case: During manual testing you notice the form validation is wrong, the success message is missing, and the redirect is broken. The agent files three separate GitHub issues with reproduction steps and blocking relationships, then prints the URLs. ## Quick Start Start a QA session and describe the bugs you have found so the agent can file them as GitHub issues.